Bayesian variable selection regression for genome-wide association studies and other large-scale problems

By Yongtao Guan, Matthew Stephens. 2011

380 citations recorded by the source corpus.

We consider applying Bayesian Variable Selection Regression, or BVSR, to genome-wide association studies and similar large-scale regression problems. Currently, typical genome-wide association studies measure hundreds of thousands, or millions, of genetic variants (SNPs), in thousands or tens of thousands of individuals, and attempt to identify regions harboring SNPs that affect some phenotype or outcome of interest. This goal can naturally be cast as a variable selection regression problem, with the SNPs as the covariates in the regression. Characteristic features of genome-wide association studies include the following: (i) a focus primarily on identifying relevant variables, rather than on prediction; and (ii) many relevant covariates may have tiny effects, making it effectively impossible to confidently identify the complete "correct" subset of variables. Taken together, these factors put a premium on having interpretable measures of confidence for individual covariates being included in the model, which we argue is a strength of BVSR compared with alternatives such as penalized regression methods. Here we focus primarily on analysis of quantitative phenotypes, and on appropriate prior specification for BVSR in this setting, emphasizing the idea of considering what the priors imply about the total proportion of variance in outcome explained by relevant covariates. We also emphasize the potential for BVSR to estimate this proportion of variance explained, and hence shed light on the issue of "missing heritability" in genome-wide association studies.

Subfields: Genetics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/1c1d9a7c9a51fbd2046a6c2262a24ecb4ed37b3d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Genetics

In Statistics and Probability

Citations in the corpus

The genomics of local adaptation in trees: are we out of the woods yet? (2017, background): “…(infinitesimal) or measureable (moderate to large) effect, the proportion of PVE explained by genetic loci with measurable effects (PGE), and the number of loci with measurable effects that underlie the trait (for more details see Guan & Stephens 2011; Zhou et al. 2014; Gompert et al. 2016).”
Integrating Functional Data to Prioritize Causal Variants in Statistical Fine-Mapping Studies (2014, methodology): “Despite having access to individual level data, variable selection strategies [13,14] were less accurate than PAINTOR in our simulations (see Figure 2 and Table 1).”
Panning for gold: ‘model‐X’ knockoffs for high dimensional controlled variable selection (2016, methodology): “, 2009; He and Lin, 2011) and Bayesian regression (Guan and Stephens, 2011; Li et al., 2011), but both approaches still suffer from a lack of type I error control (without making strong assumptions on parameter priors).”
Scalable Variational Inference for Bayesian Variable Selection in Regression, and Its Accuracy in Genetic Association Studies (2012, methodology): “We would like to pursue the Bayesian approach to variable selection for genome-wide associations studies, and though sophisticated MCMC methods have been designed for this problem (Bottolo and Richardson 2010; Guan and Stephens 2011), they can take weeks to produce reasonably accurate inferences .”
Polygenic prediction via Bayesian regression and continuous shrinkage priors (2018, methodology): “…and Goddard, 2004; Meuwissen et al., 2001; Verbyla et al., 2009, 2010; Yi et al., 2003], BayesR [Erbe et al., 2012; Moser et al., 2015], BVSR [Guan and Stephens, 2011], BSLMM [Zhou et al., 2013], and DPR [Zeng and Zhou, 2017], have used discrete mixture priors on SNP effect sizes, we expect…”
FINEMAP: efficient variable selection using summary data from genome-wide association studies (2015, methodology): “Approaches for Bayesian analysis of multi-SNP GWAS data include exhaustive search as implemented in software BIMBAM (Servin and Stephens, 2007), MCMC algorithms (Guan and Stephens, 2011), variational approximations (Carbonetto and Stephens, 2012) and stochastic search as implemented in software GUES”
Fine-mapping from summary data with the “Sum of Single Effects” model (2021, methodology): “We compared methods based on both their posterior inclusion probabilities (PIPs) [44] and credible sets (CSs) [2, 17].”
Panning for Gold: Model-free Knockoffs for High-dimensional Controlled Variable Selection (2016, methodology): “…approaches to improve power in genome-wide association studies using both penalized (Wu et al., 2009; He and Lin, 2011) and Bayesian regression (Guan and Stephens, 2011; Li et al., 2011), but both approaches still suffer from a lack of Type I error control (without making strong assumptions on…”